Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 127296
    Prev
    Next
    INDEX
    Explanations

    names of locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thugs
    -0.06
    Logs
    -0.06
    )(↵
    -0.06
     추
    -0.06
    정부
    -0.05
    .cells
    -0.05
    ันด
    -0.05
    (surface
    -0.05
    <U
    -0.05
                                                             
    -0.05
    POSITIVE LOGITS
    (Model
    0.07
    .Enabled
    0.07
     JsonResult
    0.07
    lover
    0.07
    <typename
    0.06
     fore
    0.06
     uber
    0.06
    促
    0.06
     ความ
    0.06
     Egyptians
    0.06
    Activations Density 0.022%

    No Known Activations